BP人工神经网络南疆红枣颜色分级方法的研究  

Research of the BP Artificial Neural Network in Southern Jujube Color Classification Method

作　　者：詹映[1] 罗华平[1,2] 彭云发 罗雪宁 

机构地区：[1]塔里木大学机械电气化工程学院,阿拉尔843300 [2]新疆维吾尔自治区普通高等学校现代农业工程重点实验室,阿拉尔843300

出　　处：《食品工业》2015年第1期165-167,共3页The Food Industry

基　　金：国家自然基金项目资助(No.10964009和No.11164023)

摘　　要：以南疆红枣颜色分级为研究对象,从预处理后的红枣图像中提取红体均值(R)、绿体均值(G)和蓝体均值(B)以及它们的均方差σR、σG、σB共6种颜色特征变量;再将图像从RGB到HIS颜色空间转换,然后从HIS颜色空间中,提取色度均值(H)、亮度均值(I)和饱和度均值(S)以及它们的各自的均方差σH、σS、σI共6个颜色特征变量,总计12个颜色特征变量,最后应用BP神经网络进行红枣颜色分级。结果表明,BP人工神经网络分级与人工分级的一致度达到了91.6%,该网络分级效果良好,能较好地满足红枣颜色分级的需求,对南疆红枣产品的生产、销售具有一定的理论指导和实际应用意义。With southern Xinjiang jujube color classification as the research object, then extracting the red mean （R）, green mean （G）, blue mean （B） and their mean square error σR, σG, σB and a total of 6 kinds of color characteristic variables from jujube image after preprocessing. Further making the image color spatial switching from RGB to HIS, then for the HIS color space, extracting the hue mean （H）, intensity mean （I）, saturation mean （-S） and their mean square error σH, σs, σ1 and the total of 6 kinds of color characteristic variables, the total of 12 color characteristic variables. Finally, to do the jujube color classification in applying of BP neural network. The results show that the consistent degree reached 91.6% with BP artificial neural network classification and artificial classification. The effect of this network in classification is good, and can well meet the needs of jujube color classification. There is a certain theoretical guidance and practical application significance of the production and sales for southern Xinjiang jujube.

关 键 词：南疆红枣 BP人工神经网络 颜色分级 机器视觉 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]